Personalized health early warning and diagnosis and treatment system

Abstract

The invention discloses a personalized health early warning and diagnosis and treatment system, and relates to the technical field of intelligent monitoring, and the system comprises: data acquisition and preprocessing: wearing a corresponding watch and using a corresponding applet to complete wearing management and user registration respectively, and providing personal body information in the registration process, such as height, age and medical history; by wearing the watch, information such as heart rate, blood oxygen, pulse and breath of a user in 24 hours can be collected through a photoelectric sensor, and anonymization processing is automatically carried out and then the information is uploaded and stored; basic information, namely age, gender, height, weight, medical history and the like, of the user is coded. According to the method, real-time health state assessment, risk early warning and personalized diagnosis and treatment suggestions are provided for users through health data analysis of various time sequences, personalized health assessment and early warning reports, risk assessment based on multi-physiological index monitoring and multi-dimensional sequence joint modeling and the like.

Description

Technical Field

[0001] This invention relates to the field of intelligent monitoring technology, specifically a personalized health early warning and diagnosis system. Background Technology

[0002] Wearable smart health devices are a type of portable electronic device that can be worn directly on the body and integrates multiple sensors and intelligent algorithms. They can monitor users' physiological indicators (such as heart rate, blood oxygen, body temperature, sleep quality, etc.) and exercise data (steps, activity level, calorie consumption, etc.) in real time. By connecting to a mobile APP or cloud platform, they can integrate and analyze the data to provide users with health status assessment, exercise suggestions, and warnings of potential health risks. This helps users manage their health scientifically and improve their lifestyle habits. They are widely used in daily health monitoring, fitness training, chronic disease management, and other scenarios, and are a typical product of the deep integration of the Internet of Things and health management.

[0003] Existing wearable smart health devices often only analyze single indicators and typically only provide trend charts, lacking personalized, targeted early warnings and interventions. Meanwhile, most existing Western medicine models rely on hospital patient data, lacking corresponding sample data and analytical indicators for the daily management of healthy individuals. Existing traditional Chinese medicine models cannot make good use of existing classic medical cases and traditional Chinese medicine theories, and cannot utilize machine learning models for simulation modeling and analysis. Summary of the Invention

[0004] To address the problems mentioned in the background art, the present invention aims to provide a personalized health early warning and treatment system, which has the advantages of monitoring and providing early warning of patients' health status in multiple dimensions. It solves the problem that existing TCM models cannot make good use of existing classic medical cases and TCM theories, and cannot use machine learning models for simulation modeling and analysis.

[0005] To achieve the above objectives, the present invention provides the following technical solution: a personalized health early warning and treatment system, the system comprising, Data collection and preprocessing: Wear the corresponding watch and use the corresponding mini-program to complete the wearing management and user registration respectively. During the registration process, personal physical information such as height, age and medical history is provided. By wearing a watch, the system can collect information such as heart rate, blood oxygen, pulse, and respiration from the user over 24 hours through photoelectric sensors, and automatically anonymize and then upload and save the data. Encode the user's basic information, such as age, gender, height, weight, and medical history; For the 24-hour continuous multidimensional time series data collected by the smartwatch, we use a segmented processing method to calculate the average value and fill in missing values. For example, we calculate the average value and fill in missing values ​​for the data from 8:00 to 8:10 every day. Fusion Model: After encoding basic personal information using meta-algorithms to extract modal features, and extracting features from multidimensional time series using generative adversarial models, the two types of features are then fused to form a multi-module fusion model. Through meta-information feature extraction, personalized characteristics of human constitution can be extracted. These groups typically exhibit similar index fluctuation patterns, effectively distinguishing differences between different groups. Through multidimensional generative adversarial models, not only can the change patterns of single-dimensional data be represented, but the interaction relationships between multidimensional data can also be captured, which helps to more effectively establish the body's homeostatic patterns. Model Inference and Health Report: Using a fusion model to predict the homeostasis of the human body, when the various indicators of the human body are within the range of changes in the overall homeostasis, only reasonable health management advice needs to be provided to the user; otherwise, based on the existing TCM statistical diagnostic results, detailed diagnostic opinions and health risk warnings are given, along with corresponding conditioning suggestions and medical treatment guidelines.

[0006] As a preferred embodiment of the present invention, the encoding in data acquisition and preprocessing specifically includes: segmenting age into segments, such as under 19 years old, 20-29 years old, 30-39 years old, 40-49 years old, 50-59 years old, and over 60 years old; calculating the BMI value for height and weight and then segmenting them; and performing one-hot encoding on medical history.

[0007] As a preferred embodiment of the present invention, the multidimensional time series data adopts a time series analysis module. During the time training and modeling process, the interrelationships between various dimensional information, such as the synchronization of pulse and respiration, are used to characterize the homeostatic features of the human body through multidimensional information relationships. The model integrates the information of the human body's overall homeostatic state.

[0008] Compared with the prior art, the beneficial effects of the present invention are as follows: 1. This invention encodes basic user information, such as age, gender, height, weight, and medical history. Here, we segment and encode age, such as under 19 years old, 20-29 years old, 30-39 years old, 40-49 years old, 50-59 years old, and over 60 years old; height and weight are calculated based on BMI values ​​and then segmented and encoded; medical history is one-hot encoded. This encoding method preserves the segmentation of the original information (human health status or types of susceptibility to diseases are usually closely related to an individual's age group) and prevents the inability to extract important information due to too many categories when processing category-based data.

[0009] 2. This invention uses 24-hour continuous multi-dimensional time series data collected from smartwatches. We employ a segmented processing method to calculate the average value and fill in missing values. For example, we calculate the average value and fill in missing values ​​for the data from 8:00 to 8:10 every day. The advantage of doing this is that when we analyze relevant data for a continuous week, we find that the collected time series information all exhibits 24-hour diurnal rhythm and periodicity. By using sliding window processing, we can maintain the original rhythmic pattern of the time data while avoiding the difference in the units of measurement between different types of data.

[0010] 3. This invention can extract personalized characteristics of human constitution through meta-information feature extraction. Such groups usually exhibit similar index fluctuation patterns, thus effectively distinguishing the differences between different groups. Through a multi-dimensional generative adversarial model, it can not only characterize the change pattern of single-dimensional data, but also capture the interaction relationship between multi-dimensional data, which helps to more effectively establish the homeostatic pattern of the human body.

[0011] 4. By combining a multi-module fusion model with TCM statistical diagnostic results, this invention can simultaneously consider individual differences in constitution and the overall health status of the human body, providing targeted personalized health reports and risk management suggestions; it avoids misjudgments caused by a single model or single indicator; during data collection and preprocessing, the multi-dimensional time series information of 24 consecutive hours ensures the effectiveness of data collection, while the moving average method based on window data preserves the rhythmic pattern of the original data, which helps to better identify the periodicity and rhythm of changes in human physiological indicators during model training. Attached Figure Description

[0012] Figure 1 This is a schematic diagram of the system flow of the present invention; Figure 2 This is a detailed schematic diagram of the system flow of the present invention; Figure 3 This is a detailed flowchart of the system process of the present invention. Detailed Implementation

[0013] To make the above-mentioned objects, features and advantages of the present invention more apparent and understandable, the specific embodiments of the present invention will be described in detail below with reference to the accompanying drawings.

[0014] Many specific details are set forth in the following description in order to provide a full understanding of the invention. However, the invention may also be practiced in other ways different from those described herein, and those skilled in the art can make similar extensions without departing from the spirit of the invention. Therefore, the invention is not limited to the specific embodiments disclosed below.

[0015] Secondly, the term "an embodiment" or "embodiment" as used herein refers to a specific feature, structure, or characteristic that may be included in at least one implementation of the present invention. The phrase "in one embodiment" appearing in different places throughout this specification does not necessarily refer to the same embodiment, nor is it a single embodiment or an embodiment selectively excluded from other embodiments.

[0016] Secondly, the present invention is described in detail with reference to the schematic diagrams. When detailing the embodiments of the present invention, for ease of explanation, the cross-sectional views illustrating the device structure may be partially enlarged, not according to the usual scale. Furthermore, the schematic diagrams are merely examples and should not limit the scope of protection of the present invention. In addition, actual fabrication should include three-dimensional spatial dimensions of length, width, and depth. Example

[0017] Reference Figures 1 to 3 The first embodiment of the present invention provides data collection and preprocessing: wearing the corresponding watch and using the corresponding mini-program to complete the wearing management and user registration respectively, and providing personal body information such as height, age and medical history during the registration process; By wearing a watch, the system can collect information such as heart rate, blood oxygen, pulse, and respiration from the user over 24 hours through photoelectric sensors, and automatically anonymize and then upload and save the data. Encode the user's basic information, such as age, gender, height, weight, and medical history; For the 24-hour continuous multidimensional time series data collected by smartwatches, a segmented processing method is used to calculate the average value and fill in missing values. For example, the average value and missing values ​​are filled in for the data from 8:00 to 8:10 every day. During the data processing and analysis, it was found that the changes in various indicators of different users have certain diurnal rhythms and periods, usually within 24 hours. It was proposed that data standardization and missing value imputation be performed on data for different time periods to ensure the rhythmic change characteristics after data preprocessing, which helps to train a model that is more in line with the physiological change trend of the human body. Based on wearable devices, multidimensional continuous time series information such as heart rate, pulse, respiration, blood oxygen, and body temperature is collected to construct a multivariate time series analysis module. During the time training and modeling process, the interrelationships between various dimensions of information, such as the synchronization of pulse and respiration, are used to characterize the steady-state characteristics of the human body through multidimensional information relationships. The model integrates the comprehensive steady-state information of the human body. Basic personal information, such as height, weight, age, and medical history, is collected, encoded, and then used to construct a user metadata extraction module. This module enables the encoding of characteristics between individuals within the same group and those with different physical constitutions, facilitating personalized diagnosis. Fusion Model: After encoding basic personal information using meta-algorithms to extract modal features, and extracting features from multidimensional time series using generative adversarial models, the two types of features are then fused to form a multi-module fusion model. Through meta-information feature extraction, personalized characteristics of human constitution can be extracted. These groups typically exhibit similar index fluctuation patterns, effectively distinguishing differences between different groups. Through multidimensional generative adversarial models, not only can the change patterns of single-dimensional data be represented, but the interaction relationships between multidimensional data can also be captured, which helps to more effectively establish the body's homeostatic patterns. By integrating modules from GAN and LSTM, a multi-modal fusion model is constructed, which, based on unsupervised learning, can better simulate the stable state of individuals and groups. Model Inference and Health Report: Using a fusion model to predict the homeostasis of the human body, when the various indicators of the human body are within the range of changes in the overall homeostasis, only reasonable health management advice needs to be provided to the user; otherwise, combined with the existing TCM statistical diagnostic results, detailed diagnostic opinions and health risk warnings are given, along with corresponding conditioning suggestions and medical treatment guidelines. By combining theoretical models of TCM statistical diagnosis with new fusion models, personalized assessments and health evaluation opinions are provided for users' overall health status and major disease risks. The coding in data collection and preprocessing specifically includes: segmenting age into categories such as under 19, 20-29, 30-39, 40-49, 50-59, and over 60; calculating BMI values ​​for height and weight before segmenting them; and using one-hot encoding for medical history. Multidimensional time series data are analyzed using a time series analysis module. During the time training and modeling process, the relationships between various dimensions of information, such as the synchronization of pulse and respiration, are used to characterize the homeostatic features of the human body. The model then integrates the information of the human body's overall homeostasis. In summary, through the analysis of various time-series health data, personalized health assessments and early warning reports, and risk assessments based on the monitoring of multiple physiological indicators and multidimensional sequence joint modeling, we provide users with real-time health status assessments, risk warnings, and personalized medical advice. It is important to note that the constructions and arrangements of this application shown in several different exemplary embodiments are merely illustrative. Although only a few embodiments are described in detail in this disclosure, those who consult this disclosure will readily understand that many modifications are possible (e.g., changes in the size, dimensions, structure, shape, and proportions of various elements, as well as parameter values ​​(e.g., temperature, pressure, etc.), mounting arrangements, use of materials, color, orientation, etc.) without substantially departing from the novel teachings and advantages of the subject matter described in this application). For example, an element shown as integrally formed may be composed of multiple parts or elements, the position of elements may be inverted or otherwise altered, and the nature or number or position of discrete elements may be changed or altered. Therefore, all such modifications are intended to be included within the scope of the invention. The order or sequence of any process or method steps may be changed or rearranged according to alternative embodiments. In the claims, any "device plus function" clause is intended to cover the structure described herein that performs the function, and not only structurally equivalent but also equivalent in structure. Other substitutions, modifications, alterations, and omissions may be made in the design, operation, and arrangement of the exemplary embodiments without departing from the scope of the invention. Therefore, the present invention is not limited to the specific embodiments, but extends to various modifications that still fall within the scope of the appended claims.

[0018] Furthermore, in order to provide a concise description of exemplary embodiments, not all features of actual embodiments (i.e., those features that are not relevant to the best mode of carrying out the invention as currently considered, or those features that are not relevant to implementing the invention) may be omitted.

[0019] It should be understood that numerous specific implementation decisions can be made during the development of any practical implementation, such as in any engineering or design project. Such development efforts may be complex and time-consuming, but for those skilled in the art who benefit from this disclosure, the development effort will be a routine work of design, manufacturing, and production without requiring much experimentation.

[0020] It should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention and are not intended to limit it. Although the present invention has been described in detail with reference to preferred embodiments, those skilled in the art should understand that modifications or equivalent substitutions can be made to the technical solutions of the present invention without departing from the spirit and scope of the technical solutions of the present invention, and all such modifications or substitutions should be covered within the scope of the claims of the present invention.

Claims

1. A personalized health early warning and treatment system, characterized in that: The system includes, Data collection and preprocessing: Wear the corresponding watch and use the corresponding mini-program to complete the wearing management and user registration respectively. During the registration process, personal physical information such as height, age and medical history is provided. By wearing a watch, the system can collect information such as heart rate, blood oxygen, pulse, and respiration from the user over 24 hours through photoelectric sensors, and automatically anonymize and then upload and save the data. Encode the user's basic information, such as age, gender, height, weight, and medical history; For the 24-hour continuous multidimensional time series data collected by the smartwatch, we use a segmented processing method to calculate the average value and fill in missing values. For example, we calculate the average value and fill in missing values ​​for the data from 8:00 to 8:10 every day. Fusion Model: After encoding basic personal information using meta-algorithms to extract modal features, and extracting features from multidimensional time series using generative adversarial models, the two types of features are then fused to form a multi-module fusion model. Through meta-information feature extraction, personalized characteristics of human constitution can be extracted. These groups typically exhibit similar index fluctuation patterns, effectively distinguishing differences between different groups. Through multidimensional generative adversarial models, not only can the change patterns of single-dimensional data be represented, but the interaction relationships between multidimensional data can also be captured, which helps to more effectively establish the body's homeostatic patterns. Model Inference and Health Report: Using a fusion model to predict the homeostasis of the human body, when the various indicators of the human body are within the range of changes in the overall homeostasis, only reasonable health management advice needs to be provided to the user; otherwise, based on the existing TCM statistical diagnostic results, detailed diagnostic opinions and health risk warnings are given, along with corresponding conditioning suggestions and medical treatment guidelines.

2. The personalized health early warning and treatment system according to claim 1, characterized in that: The coding in data collection and preprocessing specifically includes: segmenting age into categories such as under 19, 20-29, 30-39, 40-49, 50-59, and over 60; calculating BMI values ​​for height and weight before segmenting them; and using one-hot encoding for medical history.

3. The personalized health early warning and treatment system according to claim 1, characterized in that: Multidimensional time series data are analyzed using a time series analysis module. During the time training and modeling process, the relationships between various dimensions of information, such as the synchronization of pulse and respiration, are used to characterize the homeostatic features of the human body. The model then integrates the information of the human body's overall homeostasis.

Images